APODEC is the acronym of Automatic Polyp Detection in Colonoscopy videos. This research line is focused on the detection and posterior localization of colorectal cancer precursor lesions (polyps) in the intestine during colonoscopy explorations.
APODEC is built from a model of polyp appearance; this model was created considering image acquisition and generation process. This model also takes into account the impact of other elements of the endoluminal scene such as specular highlights, blood vessels, the luminal region and even the black border surrounding the view of the scene!
The output of APODEC are WM-DOVA energy maps, which represent for a given pixel the likelihood of a given pixel to be part of a polyp. These maps foster continuity, concavity and completeness of polyp contours (identified as valleys in the intensity image) in order to discriminate them to other polyp-like structures in the image such as folds.
APODEC has been validated in 3 different still-frame based databases (two of them proprietary of our research group) and in 2 different video-based databases. Please take a look at the following video (honorable mention at DDW2017) to see how APODEC works!
More information about WM-DOVA maps and APODEC validation:
[1] Bernal, J., Sánchez, F. J., Fernández-Esparrach, G., Gil, D., Rodríguez, C., & Vilariño, F. (2015). WM-DOVA maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physicians. Computerized Medical Imaging and Graphics, 43, 99-111.
[2] Fernández-Esparrach, G., Bernal, J., López-Cerón, M., Córdova, H., Sánchez-Montes, C., de Miguel, C. R., & Sánchez, F. J. (2016). Exploring the clinical potential of an automatic colonic polyp detection method based on the creation of energy maps. Endoscopy, 48(09), 837-842.